Text Generation Models — Page 1002

OsmosisProofling-GRPO-NT

sqlcoder-qwen2.5-coder-7b-instruct-grpo-n5-b256-t0.6-lr1e-6_global_step_60

llama3-8b-code-extended

model_sft_lora_merged

LinYi-Full-Model

model_sft_resta

model_sft_dare_resta

sanatan-gita-guru-full

Mistral-7B-Erebus-v3

model_sft_dare

llama2-13b-math-lm-ties-merged

llama2-13b-math-lm-obf-merged

model_sft_dare_resta

Qwen3-1.7B

llama3.2-4oClaude

ds1p5b_kywork_math-global_step_400

llama8b-er-v1-jb-seed2_lora

Qwen2.5-Coder-0.5B-Instruct-Gensyn-Swarm-pudgy_horned_caterpillar

teacher_prefix_minesweeper_kukurasu_continual_Qwen3_4B_Thinking_nemotron_cascade_8b

teacher_prefix_minesweeper_kukurasu_continual_Qwen3_4B_Thinking_qwen3-1.7b

affine-5FvrSLALm2SHak4kAeZMqgTWmCZNaCDwHzoeGZ4uaqcMKuju

Qwen2.5-7B-Instruct-es-em-bad-medical-advice

ultrafeedbackSkyworkAgree_alignmentZephyr7BSftFull_sdpo_score_ebs128_lr1e-06_3

GRPO_Best13_Linear_topk_820_official

affine-test1-5CYCiLKFhU5TwbqBf1TnQHJvq2d4HcHC7WuKffhWEBhReS4V

qwen3_0.6b_gsm8k

HOTHUN-Hermes-3-8B-v1.1

Qwen3-4B-ZH-SynthDolly-1A-E5

qwen2_5_1_5b_demo

model_sft_dare_resta

Qwen3-8B-D8K

qwen-medical-sft-merged

Qwen3-0.6B-Reverse-Text-JSD-10

model_sft_lora

qwen-2.5-1.5b-multiwoz-finetuned

deepseek-r1-sft

data-cleaning-grpo

affine-p3-5FcH1JkFM4gTvrZWdcMcqTvaxYxoMDfArYXcJUqdaFej1qbD

mpq3_qwen4bi_sft_dpo_beta1e-1_step7680

mpq3_qwen4bi_sft_dpo_beta1e-1_step9216

Llama-3.2-3B-Instruct-PT-SynthDolly-1A-E8

lorel.ai_long_train